The DOI matches its Crossref record; 61 of the 61 references it cites were found in a registry or an index.
MetaFormer is Actually What You Need for Vision
Open accessAbstract
Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in transformers can be replaced by spatial MLPs and the resulted models still perform quite well. Based on this observation, we hypothesize that the general architecture of the transformers, instead of the specific token mixer module, is more essential to the model's performance. To verify this, we deliberately replace the attention module in transformers with an embarrassingly simple spatial pooling operator to conduct only basic token mixing. Surprisingly, we observe that the derived model, termed as PoolFormer, achieves competitive performance on multiple computer vision tasks. For example, on ImageNet-1K, PoolFormer achieves 82.1 % top-1 accuracy, surpassing well-tuned vision transformer/MLP-like baselines DeiT-B/ResMLP-B24 by 0.3%/1.1% accuracy with 35%/52% fewer parameters and 49%/61% fewer MACs. The effectiveness of Pool-Former verifies our hypothesis and urges us to initiate the concept of “MetaFormer”, a general architecture abstracted from transformers without specifying the token mixer. Based on the extensive experiments, we argue that MetaFormer is the key player in achieving superior results for recent transformer and MLP-like models on vision tasks. This work calls for more future research dedicated to improving MetaFormer instead of focusing on the token mixer modules. Additionally, our proposed PoolFormer could serve as a starting baseline for future MetaFormer architecture design.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2016) · arXiv · doi:10.48550/arxiv.1606.00915 · Cited by 22,392
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392
Xception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.195 · Cited by 20,380
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · arXiv · doi:10.48550/arxiv.2005.12872 · Cited by 18,253
Learning Internal Representations by Error Propagation
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985) · doi:10.21236/ada164453 · Cited by 16,172
(2010) · Cited by 14,134
(2010) · International Conference on Machine Learning · Cited by 13,995
Kaugeranna, R., Kaugeranna, E., & Aion, (. S. 4. 6. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.giscience.2023.43 · Cited by 13,690
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
Aggregated Residual Transformations for Deep Neural Networks
Xie, S., Girshick, R., Dollar, P., Tu, Z., & He, K. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.634 · Cited by 12,465
mixup: Beyond Empirical Risk Minimization
Zhang, H., Cisse, M., Dauphin, Y. N., & Lopez-Paz, D. (2017) · arXiv · doi:10.48550/arxiv.1710.09412 · Cited by 5,831
CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features
Yun, S., Han, D., Chun, S., Oh, S. J., Yoo, Y., & Choe, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00612 · Cited by 5,400
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., & Shao, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00061 · Cited by 5,259 · cited 4×
“Similar to [23, 35, 55], PoolFormer adopts hierarchical architecture with 4 stages.”
BackgroundMethodInfluentialRandom Erasing Data Augmentation
Zhong, Z., Zheng, L., Kang, G., Li, S., & Yang, Y. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.7000 · Cited by 3,617
Gaussian Error Linear Units (GELUs)
Hendrycks, D., & Gimpel, K. (2016) · arXiv · doi:10.48550/arxiv.1606.08415 · Cited by 3,537
Scene Parsing through ADE20K Dataset
Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.544 · Cited by 3,326
Randaugment: Practical automated data augmentation with a reduced search space
Cubuk, E. D., Zoph, B., Shlens, J., & Le, Q. V. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00359 · Cited by 3,223
CvT: Introducing Convolutions to Vision Transformers
Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., & Zhang, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00009 · Cited by 2,444
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z., Tay, F. E. H., Feng, J., & Yan, S. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00060 · Cited by 2,415
Self-citationTokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z., Tay, F. E., Feng, J., & Yan, S. (2021) · arXiv · doi:10.48550/arxiv.2101.11986 · Cited by 2,415
Self-citationMMDetection: Open MMLab Detection Toolbox and Benchmark
Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., et al. (2019) · arXiv · doi:10.48550/arxiv.1906.07155 · Cited by 2,227
Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning
Elfwing, S., Uchibe, E., & Doya, K. (2018) · Neural Networks · doi:10.1016/j.neunet.2017.12.012 · Cited by 2,119
Deep Networks with Stochastic Depth
Huang, G., Sun, Y., Liu, Z., Sedra, D., & Weinberger, K. Q. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_39 · Cited by 2,104
MLP-Mixer: An all-MLP Architecture for Vision
Tolstikhin, I., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Yung, J., Steiner, A., Keysers, D., Uszkoreit, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2105.01601 · Cited by 2,087
Designing Network Design Spaces
Radosavovic, I., Kosaraju, R. P., Girshick, R., He, K., & Dollar, P. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01044 · Cited by 2,084
PRINCIPLES OF NEURODYNAMICS. PERCEPTRONS AND THE THEORY OF BRAIN MECHANISMS
ROSENBLATT, F. (1961) · doi:10.21236/ad0256582 · Cited by 1,691
Panoptic Feature Pyramid Networks
Kirillov, A., Girshick, R., He, K., & Dollár, P. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00656 · Cited by 1,460
Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., & Wang, Y. (2021) · arXiv · doi:10.48550/arxiv.2103.00112 · Cited by 1,394 · cited 1×
“Based on this common belief, many variants of the attention modules [13, 21, 55, 66] have been developed to improve the vision transformer.”
BackgroundGoing deeper with Image Transformers
Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., & Jegou, H. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00010 · Cited by 1,259
(2020) · International Conference on Machine Learning · Cited by 1,012
CMT: Convolutional Neural Networks Meet Vision Transformers
Guo, J., Han, K., Wu, H., Tang, Y., Chen, X., Wang, Y., & Xu, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01186 · Cited by 1,005
Stand-Alone Self-Attention in Vision Models
Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., & Shlens, J. (2019) · arXiv · doi:10.48550/arxiv.1906.05909 · Cited by 977
ResMLP: Feedforward networks for image classification with data-efficient training
Touvron, H., Bojanowski, P., Caron, M., Cord, M., El-Nouby, A., Grave, E., Izacard, G., Joulin, A., Synnaeve, G., Verbeek, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2105.03404 · Cited by 807
ResMLP: Feedforward Networks for Image Classification With Data-Efficient Training
Touvron, H., Bojanowski, P., Caron, M., Cord, M., El-Nouby, A., Grave, E., Izacard, G., Joulin, A., Synnaeve, G., Verbeek, J., et al. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3206148 · Cited by 807
ConViT: improving vision transformers with soft convolutional inductive biases
d’Ascoli, S., Touvron, H., Leavitt, M. L., Morcos, A. S., Biroli, G., & Sagun, L. (2022) · Journal of Statistical Mechanics: Theory and Experiment · doi:10.1088/1742-5468/ac9830 · Cited by 782
FNet: Mixing Tokens with Fourier Transforms
Lee-Thorp, J., Ainslie, J., Eckstein, I., & Ontanon, S. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2022.naacl-main.319 · Cited by 519
Scaling Local Self-Attention for Parameter Efficient Visual Backbones
Vaswani, A., Ramachandran, P., Srinivas, A., Parmar, N., Hechtman, B., & Shlens, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01270 · Cited by 453
Rethinking and Improving Relative Position Encoding for Vision Transformer
Wu, K., Peng, H., Chen, M., Fu, J., & Chao, H. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00988 · Cited by 371
How Do Vision Transformers Work?
Park, N., & Kim, S. (2022) · arXiv · doi:10.48550/arxiv.2202.06709 · Cited by 356 · cited 1×
“[41] shows that multi-head self-attentions improve accuracy and generalization by flattening the loss landscapes.”
BackgroundEfficient Cipher-Only Attack of a Stream Cipher in RDHEI Based on Pixel Smoothness Estimation
Chen, Y., Li, Z., Liu, B., Zhang, J., Yin, B., & He, H. (2019) · EasyChair Preprints · doi:10.29007/3b2l · Cited by 232
Simplifying ConvNets for Fast Learning
Mamalet, F., & García, C. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33266-1_8 · Cited by 154
CycleMLP: A MLP-like Architecture for Dense PredictionPreprint
Chen, S., Xie, E., Ge, C., Chen, R., Liang, D., & Luo, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.10224 · Cited by 128
Refiner: Refining Self-attention for Vision TransformersPreprint
Zhou, D., Shi, Y., Kang, B., Yu, W., Jiang, Z., Li, Y., Jin, X., Hou, Q., & Feng, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.03714 · Cited by 67
Self-citationSparse and Continuous Attention MechanismsPreprint
Martins, A. F. T., Farinhas, A., Treviso, M. V., Niculae, V., Aguiar, P. M. Q., & Figueiredo, M. A. T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.07214 · Cited by 26
∞-former: Infinite Memory Transformer.Preprint
Martins, P. H., Marinho, Z., & Martins, A. F. T. (2021) · arXiv (Cornell University) · Cited by 11
Research works printed but not linked: 14
- liu, 2021, Pay attention to mlps, ArXiv Preprint
- lei ba, 2016, Layer normalization, ArXiv Preprint
- hou, 2021, Vision permutator: A permutable mlp-like architecture for visual recognition, ArXiv Preprint
- touvron, 0, Training data-efficient image transformers & distillation through attention, International Conference on Machine Learning, 10347
- wightman, 2021, Resnet strikes back: An improved training procedure in timm, ArXiv Preprint
- wightman, 2019, pytorch-image-models
- vaswani, 0, Attention is all you need, Advances in neural information processing systems, 5998
- contributors, 2020, MMSegmentation Openmmlab semantic segmentation toolbox and benchmark
- d'ascoli, 2021, Convit: Improving vision transformers with soft convolutional inductive biases, Proceedings of the 38th International Conference on Machine Learning volume 139 of Proceedings of Machine Learning Research, 2286
- dong, 2021, Attention is not all you need: Pure attention loses rank doubly exponentially with depth, ArXiv Preprint
- dosovitskiy, 0, An image is worth 16×16 words: Transformers for image recognition at scale, International Conference on Learning Representations
- chen, 2018, A^ 2-nets: Double attention networks, Advances in neural information processing systems, 31, 352
- raghu, 2021, Do vision transformers see like convolutional neural networks?, ArXiv Preprint
- rao, 2021, Global filter networks for image classification, ArXiv Preprint
Cited by
Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks
Chen, J., Kao, S.-H., He, H., Zhuo, W., Wen, S., Lee, C.-H., & Chan, S.-H. G. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01157 · Cited by 2,343
Scaling Up Your Kernels to 31×31: Revisiting Large Kernel Design in CNNs
Ding, X., Zhang, X., Han, J., & Ding, G. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01166 · Cited by 1,447
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Wang, W., Dai, J., Chen, Z., Huang, Z., Li, Z., Zhu, X., Hu, X., Lu, T., Lu, L., Li, H., et al. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01385 · Cited by 1,080
Self-citationGuo, M.-H., Lu, C.-Z., Liu, Z.-N., Cheng, M.-M., & Hu, S.-M. (2023) · Computational Visual Media · doi:10.1007/s41095-023-0364-2 · Cited by 1,073
EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention
Liu, X., Peng, H., Zheng, N., Yang, Y., Hu, H., & Yuan, Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01386 · Cited by 956
Metadata
- Authors
- Yu, W., Luo, M., Zhou, P., Si, C., Zhou, Y., Wang, X., Feng, J., & Yan, S.
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2022-06
- Pages
- 10809-10819
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4312820606
- Cited by
- 1,255
- References
- 61
- FWCI
- 103.05
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.